Classifying Defects in Pallet Stringers by Ultrasonic Scanning
Keywords:Ultrasonic scanning, nondestructive testing, transducer, defect classification, neural network
AbstractDetecting and classifying defects are required to grade and sort pallet parts. Use of quality parts can extend the life cycle of pallets and can reduce long-term cost. An investigation has been carried out to detect and classify defects in yellow-poplar (Liriodendron tulipifera, L.) and red oak (Quercus rubra, L.) stringers using ultrasonic scanning. Data were collected for sound and unsound knots, bark pockets, decay, holes, and wane using rolling transducers in a pitch-catch arrangement. Data from eight ultrasonic variables—energy, pulse length, time of flight (TOF)-amplitude, TOF-energy, TOF-centroid, energy value, energy pulse value, and peak frequency—were used to classify defects. Three different types of classifiers were used to categorize defects—a multi-layer perceptron network (MLP), a probabilistic neural network (PNN), and a k-nearest neighbor (KNN) classifier. Mean values for the energy variables demonstrated statistically significant differences between clear wood and defects and among defect types. Mean values for the TOF variables did not differ significantly between clear wood and knots. All three types of classifiers were able to distinguish defected from clear wood in oak with accuracies above 95%; accuracies for yellow-poplar were somewhat lower for the MLP and PNN classifiers. Among the defect classes, decay exhibited the highest recognition rate for both yellow-poplar and oak. Wane and holes in oak were readily confused owing to their common loss of transducer contact. Overall accuracy at the data-point level varied from 69-78%. Simple post-processing operations are expected to improve that substantially. Based on accuracy performance alone, the MLP and KNN appear equally preferable for this task.
Araman, P. A., W. F. Winn, M. F. Kabir, X. Torcheux, and G. Loizeaud. 2003. Unsound defect volume in hardwood pallet cants. Forest Prod. J.53(2):45-49.nBradshaw, B. K., R. D. Adams, M. E. Schafer, R. J. Ross, and R. C. Pettersen. 2000. Detection of wetwood in green red oak lumber by ultrasound and gas chromatography-mass spectrometry analysis. Pages 49-56 in Proc. 12th International Symposium on Nondestructive Testing of Wood.nDuda, R. O., and P. E. Hart. 1973. Pattern classification and scene analysis. John Wiley & Sons, New York, NY.nFuller, J. J., R. J. Ross, and J. R. Dramm. 1995. Nondestructive evaluation of honeycomb and surface check in red oak lumber. Forest Prod. J.45(5):42-44.nGonzales, R. c., and r. e. woods. 1992. Digital image processing. Addison-Wesley Publishing Company, Inc., Boston, MA.nHalabe, H. B., H. V. S. Gangarao, and V. R. Hota. 1993. Nondestructive evaluation of wood using ultrasonic frequency analysis. Pages 2155-2160 in D. O. Thompson, and D. E. Chimenti, eds., Review of Progress in Quantitative Nondestructive Evaluation Vol. 13. Plenum Press, New York, NY.nHalabe, H. B., H. V. S. Gangarao, and C. E. Solomon. 1994. Nondestructive evaluation of wood using ultrasonic dr-coupled transducers. Pages 2251-2256 in D. O. Thompson, and D. E. Chimenti, eds., Review of Progress in Quantitative Nondestructive Evaluation. Vol. 12. Plenum Press, New York, NY.nHalabe, H. B., H. V. S. Gangarao, S. H. Petro, and V. R. Hota. 1996. Assessment of defects and mechanical properties of wood members using ultrasonic frequency analysis. Materials Eval.54(2):314-352.nKabir, M. F., D. L. Schmoldt, and M. E. Schafer. 2000.Roller-transducer scanning of wooden pallet parts for defect detection. Review of Progress in Quantitative Nondestructive Evaluation 20:1218-1225.nKabir, M. F., D. L. Schmoldt, and M. E. Schafer. 2002. Time domain ultrasonic signal characterization for defects in thin unsurfaced hardwood lumber. Wood Fiber Sci.34(1):165-182.nKarsulovic, J. T., L. A. Leon, and L. Gaete. 2000. Ultrasonic detection of knots and annual ring orientation in Pinus radiata lumber. Wood Fiber Sci.32(3):278-286.nMcdonald, K. A. 1980. Lumber defect detection by ultrasonics. Res. Paper FPL-311, USDA Forest Serv., Forest Prod. Lab. Madison, WI. 20 pp.nNiemz, P., J. Kucera, M. Schob, and M. Scheffer. 1999. Possibility of defects detection in wood with ultrasound. Holz Roh- Werkst.57(2):96-102.nRaczkowski, J., K. Lutomski, W. Molinski, and R. Wos. 1999. Detection of early stage of wood by acoustic emission technique. Wood Sci. Technol.33(5):353-358.nRoss, R. J., J. C. Ward, and A. Tenwolde. 1992. Identifying bacterially infected oak by stress wave non-destructive evaluation. Res. Paper FPL-RP-512, USDA Forest Serv., Forest Prod. Lab., Madison, WI.nSpecht, D. F. 1990a. Probabilistic Neural Networks, Neural Networks, 3. 109-118.nSpecht, D. F. 1990b. Probabilistic Neural Networks and the Polynomial Adaline as Complementary Techniques for Classification, IEEE Transactions on Neural Networks (1):111-121.nSchmoldt, D. L., J. A. Mccleod III, and P. A. Araman. 1993. Economics of grading and sorting pallets parts. Forest Prod. J.43(11/12):19-23.nSchmoldt, M. Morrone, and J. C. Duke, Jr. 1994. Ultrasonic inspection of wooden pallets for grading and sorting. Pages 2161-2166 in D. O. Thompson, and D. E. Chimenti, eds., Review of Progress in Quantitative Nondestructive Evaluation. Vol. 12. Plenum Press, New York, NY.nSchmoldt, R. M. Nelson, R. M. Ross, and K. A. Mcdonald. 1997. Ultrasonic inspection of wooden pallet parts using time of flight. Pages 1791-1797 in D. O. Thompson, and D. E. Chimenti, eds., Review of Progress in Quantitative Nondestructive Evaluation Vol. 16. Plenum Press, New York, NY.nTiitta, M. E., F. C. Beall, and J. M. Biernacki. 2001. Classification study for using acoustic-ultrasonic to detect internal decay in glulam beams. Wood Sci. Technol. 35:85-96.n
The copyright of an article published in Wood and Fiber Science is transferred to the Society of Wood Science and Technology (for U. S. Government employees: to the extent transferable), effective if and when the article is accepted for publication. This transfer grants the Society of Wood Science and Technology permission to republish all or any part of the article in any form, e.g., reprints for sale, microfiche, proceedings, etc. However, the authors reserve the following as set forth in the Copyright Law:
1. All proprietary rights other than copyright, such as patent rights.
2. The right to grant or refuse permission to third parties to republish all or part of the article or translations thereof. In the case of whole articles, such third parties must obtain Society of Wood Science and Technology written permission as well. However, the Society may grant rights with respect to Journal issues as a whole.
3. The right to use all or part of this article in future works of their own, such as lectures, press releases, reviews, text books, or reprint books.